基于空间透视不变量的摄象机标定方法

本文给出了一种以空间不变量的数据来计算摄象机外部参数的方法．空间透视不变量是指在几何变换中如投影或改变观察点时保持不变的形状描述．由于它可以得到一个相对于外界来讲独立的物体景物的特征描述，故可以很广泛的应用到计算机视觉等方面．摄象机标定是确定摄象机摄取的２Ｄ图象信息及其３Ｄ实际景物的信息之间的变换关系，它包括内部参数和外部参数两个部分．内部参数表征的是摄象机的内部特征和光学特征参数，包括图象中心（Ｃｘ，Ｃｙ）坐标、图象尺度因子Ｓｘ、有效的焦距长度ｆ和透镜的畸变失真系数Ｋ；外部参数表示的是摄象机的位置和方向在世界坐标中的坐标参数，它包括平移矩阵Ｔ和旋转矩阵Ｒ３×３，一般情况下可以写成一个扩展矩阵［ＲＴ］３×４．本文基于空间透视不变量的计算数据，给出了一种标定摄象机外部参数的方法，实验结果表明该方法具有很强的鲁棒性．     

Self-Calibration of a Moving Camera from Point Correspondences and Fundamental Matrices

We address the problem of estimating three-dimensional motion, and structure from motion with an uncalibrated moving camera. We show that point correspondences between three images, and the fundamental matrices computed from these point correspondences, are sufficient to recover the internal orientation of the camera (its calibration), the motion parameters, and to compute coherent perspective projection matrices which enable us to reconstruct 3-D structure up to a similarity. In contrast with other methods, no calibration object with a known 3-D shape is needed, and no limitations are put upon the unknown motions to be performed or the parameters to be recovered, as long as they define a projective camera.The theory of the method, which is based on the constraint that the observed points are part of a static scene, thus allowing us to link the intrinsic parameters and the fundamental matrix via the absolute conic, is first detailed. Several algorithms are then presented, and their performances compared by means of extensive simulations and illustrated by several experiments with real images.     

Calibration of mirror position and extrinsic parameters in axial non-central catadioptric systems

We propose a novel calibration method for catadioptric systems made up of an axial symmetrical mirror and a pinhole camera with its optical center located at the mirror axis. The calibration estimates the relative camera/mirror position and the extrinsic rotation and translation w.r.t. the world frame. The procedure requires a single image of a (possibly planar) calibration object. We show how most of the calibration parameters can be estimated using linear methods (Direct-Linear-Transformation algorithm) and cross-ratio. Two remaining parameters are obtained by using non-linear optimization. We present experimental results on simulated and real images.     

基于监督的室内机器人导航系统研究

针对室内光照多变对机器视觉带来的不良影响所造成的室内机器人定位难的问题，提出了一种基于监督的室内导航模型。将鱼眼相机固定在室内房顶的中心位置，并且进行多次拍照，拍照后的图片经过图像处理，即可以完成获取整个地图，以及可行驶区域的人工标定。以屋顶固定参照物灯管为中心，结合位于机器人上的移动设备在不同位置向房顶参照物拍摄的图像数据和实际坐标位置，组成了投影轮廓数据库。根据在移动过程中机器人上的移动设备对房顶参照物进行拍摄，并与数据库匹配，实现了当前机器人的位置信息的获取。经测试，本方法在中低精度下具有一定的可行性，并且具有速度快的优点。本次研究实现了在精度要求不高情况下室内的监督导航。     

基于共面圆的距离传感器与相机的相对位姿标定

近年来, 距离传感器与摄像机的组合系统标定在无人车环境感知中得到了广泛的研究与应用, 其中基于平面特征的方法简单易行而被广泛采用. 然而, 目前多数方法基于点匹配进行, 易错且鲁棒性较低. 本文提出了一种基于共面圆的距离传感器与相机的组合系统相对位姿估计方法. 该方法使用含有两个共面圆的标定板, 可以获取相机与标定板间的位姿, 以及距离传感器与标定板间的位姿. 此外, 移动标定板获取多组数据, 根据计算得到两个共面圆的圆心在距离传感器和相机下的坐标, 优化重投影误差与3D对应点之间的误差, 得到距离传感器与相机之间的位姿关系. 该方法不需要进行特征点的匹配, 利用射影不变性来获取相机与三维距离传感器的位姿. 仿真实验与真实数据实验结果表明, 本方法对噪声有较强的鲁棒性, 得到了精确的结果.     

A paraperspective factorization method for shape and motionrecovery

The factorization method, first developed by Tomasi and Kanade (1992), recovers both the shape of an object and its motion from a sequence of images, using many images and tracking many feature points to obtain highly redundant feature position information. The method robustly processes the feature trajectory information using singular value decomposition (SVD), taking advantage of the linear algebraic properties of orthographic projection. However, an orthographic formulation limits the range of motions the method can accommodate. Paraperspective projection, first introduced by Ohta et al. (1981), is a projection model that closely approximates perspective projection by modeling several effects not modeled under orthographic projection, while retaining linear algebraic properties. Our paraperspective factorization method can be applied to a much wider range of motion scenarios, including image sequences containing motion toward the camera and aerial image sequences of terrain taken from a low-altitude airplane     

利用三目视觉获得复杂曲面的边界曲线

复杂零件表面几何模型的构造是逆向工程的研究重点，根据零件表面数据提取零件表面的边界是构造零件几何模型的关键步骤．提出了基于三目视觉方法提取和构造复杂曲面边界的技术．将一台摄像机固定在三坐标测量机(CMM)横梁上，通过沿X，Y方向移动CMM从而获得物体在空间三个不同位置的图像；从一幅图像中提取反映物体边界的特征点，通过与其他两幅图像匹配得到这些特征点的空间坐标，最后以这些特征点构造出物体边界的B样条曲线。     

Minimal parameterization of fundamental matrices using motion and camera properties

This paper addresses the optimal recovery of the displacement and projection parameters from uncalibrated monocular video sequences. We study the particular cases of camera and object displacements and camera projection in order to extract an optimized parameterization of the problem of parameter recovery for each case.

This work follows previous studies on particular cases of displacement, scene geometry and camera analysis and focuses on the particular forms of fundamental matrices. This paper introduces the idea of using not all particular cases as individual cases but grouping these cases into a tractable number of sets, using properties on fundamental matrices.

Some experiments were performed in order to demonstrate that if several models are correct, the model with the least parameters gives the best estimate, corresponding to the true case.     

Self-Calibration of Stationary Cameras

A new practical method is given for the self-calibration of a camera. In this method, at least three images are taken from the same point in space with different orientations of the camera and calibration is computed from an analysis of point matches between the images. The method requires no knowledge of the orientations of the camera. Calibration is based on the image correspondences only. This method differs fundamentally from previous results by Maybank and Faugeras on self-calibration using the epipolar structure of image pairs. In the method of this paper, there is no epipolar structure since all images are taken from the same point in space, and so Maybank and Faugeras's method does not apply. Since the images are all taken from the same point in space, determination of point matches is considerably easier than for images taken with a moving camera, since problems of occlusion or change of aspect or illumination do not occur.A non-iterative calibration algorithm is given that works with any number of images. An iterative refinement method that may be used with noisy data is also described. The algorithm is implemented and validated on several sets of synthetic and real image data.     

基于环视图象的数字相机内参数自定标方法

描述了一种适用于IBR系统的数字相机内参数自定标方法。该方法基于跟踪机机旋转得到的图象系列的特征匹配点以,而不需要标定物。认定在相机旋转过程中,其光学中心是稳定不变的,也即图象中心是固定的,可以事先定标;但容许相机的焦距在各幅图象间有变化,利用真实图象序列进行了实验验证,表明该方法能鲁棒地估算相机内参数。     

基于图像的大型物体尺寸的三维测量方法研究

针对大型物体尺寸不易测量的问题,研究简单快速的测量方法;提出了一种利用数码相机完成物体尺寸的三维测量的方法;利用数码相机从多角度获取图像,采用稳定性强的Harris角点检测算法对图像进行特征点检测;在相机标定过程中提出了一种利用图像中被测物体自适应寻找标定模板的方法,扩大了标定模板的使用范围;最后利用投影矩阵理论计算特征点的世界坐标进行测量;实验证明测量结果误差在2.0%以内,说明该方法能够克服传统测量方法的缺点,满足一般工业的测量要求并且适用范围广。     

基于二次曲线的纯旋转摄像机自标定

研究探讨了一种基于平面二次曲线的纯旋转摄像机自标定方法.在不同的方位拍摄三幅或三幅以上图像,每幅图像至少包含两个空间平面二次曲线、或两个二次曲面、或一个平面二次曲线与一个二次曲面的投影,利用图像之间的二次曲线对应关系,可以确定摄像机的内参数矩阵,同时可以获得摄像机不同方位之间的旋转矩阵.由于使用的定标基元为二次曲线,是较点和直线包含更多信息的基元,因而基元之间的匹配容易自动实现,并有助于提高标定算法的鲁棒性和在线实时性.模拟实验和真实图像实验表明文中所介绍的方法是可行的.     

Camera calibration issues in robot calibration with eye-on-hand configuration

One of the possible methods for accurate, fast, low-cost and automated robot calibration is to employ a single camera rigidly mounted to the robot end-effector together with a single camera calibration board. The end-effector pose is measured by calibration of the camera at every robot measurement configuration. This paper contends that, with several modifications, Tsai's radial alignment constraint (RAC) camera calibration method can be made a fast and sufficiently accurate pose measurement technique. This paper focuses on speed, accuracy and cost enhancement of RAC-based camera calibration. A fast RAC-based algorithm is proposed, which cuts the computation time of Tsai's original algorithm by about a 5: 1 ratio while keeping its accuracy within the tolerances required for a successful robot calibration. A low-cost method for estimation of the ratio of scale factors of the camera/vision system is also proposed. This method does not require a precision vertical micrometer stage to provide non-coplanar calibration points data for camera calibration. Finally, the phenomenon of perspective projection distortion of circular camera calibration points is fully analyzed and error compensation methods are proposed.     

基于关键姿态分析的运动图自动构建

多目标位姿估计问题是无人驾驶、人机交互等领域的基础问题之一, 但目前受采集设备限制, 该领域数据大多集中在较小空间范围, 这使得刚体位姿估计的实用价值受到限制. 针对上述问题, 提出了一种基于孪生空间的单目图像目标位姿一体化标注方法, 并设计了一套位姿标注工具 LabelImg3D. 首先, 在孪生空间中放置同焦距的虚拟相机, 并构建与真实目标等同的3维模型;然后在孪生空间中放置真实空间拍摄图像(一次投影图), 使其填充虚拟相机视场;最后对3维模型进行平移旋转, 使目标二次投影与一次投影在虚拟相机中保持一致, 从而一体化得到目标位姿. 基于该方法, 开源了一套标注工具LabelImg3D (   

Solving the recognition problem for six lines using the Dixon resultant

The “Six-line Problem” arises in computer vision and in the automated analysis of images. Given a three-dimensional (3D) object, one extracts geometric features (for example six lines) and then, via techniques from algebraic geometry and geometric invariant theory, produces a set of 3D invariants that represents that feature set. Suppose that later an object is encountered in an image (for example, a photograph taken by a camera modeled by standard perspective projection, i.e. a “pinhole” camera), and suppose further that six lines are extracted from the object appearing in the image. The problem is to decide if the object in the image is the original 3D object. To answer this question two-dimensional (2D) invariants are computed from the lines in the image. One can show that conditions for geometric consistency between the 3D object features and the 2D image features can be expressed as a set of polynomial equations in the combined set of two- and three-dimensional invariants. The object in the image is geometrically consistent with the original object if the set of equations has a solution. One well known method to attack such sets of equations is with resultants. Unfortunately, the size and complexity of this problem made it appear overwhelming until recently. This paper will describe a solution obtained using our own variant of the Cayley–Dixon–Kapur–Saxena–Yang resultant. There is reason to believe that the resultant technique we employ here may solve other complex polynomial systems.     

基于HALCON的全景摄像机标定及应用研究

现有全景摄像机标定算法中,场景的先验知识在很多情况下难以准确获取。提出了一种基于HALCON的双曲面折反射全景摄像机标定算法。通过摄像机或者标定板的相互移动来获取不同位置的标定板图像;通过HALCON预处理后提取角点坐标;通过最小二乘法求解标定点投影方程的展开系数得到相机的内外参数。该算法中摄像机只需满足单视点要求,不需要场景的先验知识,也不需要特殊的装置和设备。实验结果表明能够获得较高的标定精度,并且在足球机器人边线距离的测量中得到了准确的结果。     

基于投影仪和摄像机的结构光视觉标定方法

为实现基于投影仪和摄像机的结构光视觉系统连续扫描,需要计算投影仪投影的任意光平面与摄像机图像平面的空间位置关系,进而需要求取摄像机光心与投影仪光心之间的相对位置关系。求取摄像机的内参数,在标定板上选取四个角点作为特征点并利用摄像机内参数求取该四个特征点的外参数,从而知道四个特征点在摄像机坐标系中的坐标。利用投影仪自身参数求解特征点在投影仪坐标系中的坐标,从而计算出摄像机光心与投影仪光心之间的相对位置关系,实现结构光视觉标定。利用标定后的视觉系统,对标定板上的角点距离进行测量,最大相对误差为0.277%,表明该标定算法可以应用于基于投影仪和摄像机的结构光视觉系统。     

Matching wire frame objects from their two dimensional perspective projections

A wire frame object consists of a set of three dimensional arcs, each arc being a sequence of conics and line segments lying in the same plane, with different arcs being allowed to lie on different planes. Given a picture taken by a camera focusing on one wire frame object, we show how to determine what the object is and where it is situated relative to the camera when the camera viewing parameters are unknown.

To accomplish the object identification, we begin with a segmented picture. Then we construct a ray from the lens to each point on the boundary of every region. For each region, the collection of its associated rays is a cone. We show that by constructing cones, the two-dimensional to three-dimensional matching problem is transformed into an equivalent three-dimensional to three-dimensional matching problem.

This matching problem is expressed as a nonlinear optimization search procedure on the 6 camera viewing parameters: the 3 translation parameters and the 3 rotation parameters. A solution is found when a viewing position and optical axis is determined which is consistent with the world knowledge we have of possible curves and the observed image data.     

基于目标检测的机器人手眼标定方法

智能协作机器人依赖视觉系统感知未知环境中的动态工作空间定位目标,实现机械臂对目标对象的自主抓取回收作业。RGB-D相机可采集场景中的彩色图和深度图,获取视野内任意目标三维点云,辅助智能协作机器人感知周围环境。为获取抓取机器人与RGB-D相机坐标系之间的转换关系,提出基于yolov3目标检测神经网络的机器人手眼标定方法。将3D打印球作为标靶球夹持在机械手末端,使用改进的yolov3目标检测神经网络实时定位标定球的球心,计算机械手末端中心在相机坐标系下的3D位置,同时运用奇异值分解方法求解机器人与相机坐标系转换矩阵的最小二乘解。在6自由度UR5机械臂和Intel RealSense D415深度相机上的实验结果表明,该标定方法无需辅助设备,转换后的空间点位置误差在2 mm以内,能较好满足一般视觉伺服智能机器人的抓取作业要求。     

Estimation of mirror shape and extrinsic parameters in axial non-central catadioptric systems

We propose a method to estimate the mirror shape and position, and the extrinsic parameters in axial non-central catadioptric systems (i.e. systems with an axial symmetrical mirror and a pinhole camera with its optical center located at the mirror axis). Our method requires one or more images of a planar calibration pattern consisting of points and lines with known position (e.g. a checkerboard), and that the camera be internally calibrated. We also present an alternative algorithm for the particular case of catadioptric systems with spherical mirror, were the estimation is achieved by fitting quartic curves to the images of lines of the calibration pattern. An analytical solution is presented for every method. Each analytical solution is then refined by a non-linear optimization procedure. We present experimental results, on simulated and real images, that demonstrate the validity of our work.